{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ESZZ7R77PUR6WD4NLTRCXCFLJN","short_pith_number":"pith:ESZZ7R77","schema_version":"1.0","canonical_sha256":"24b39fc7ff7d23eb0f8d5ce22b88ab4b7f89c8eab2ec00164a505807a4137559","source":{"kind":"arxiv","id":"1805.09613","version":1},"attestation_state":"computed","paper":{"title":"A0C: Alpha Zero in Continuous Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO","cs.SY"],"primary_cat":"stat.ML","authors_text":"Aske Plaat, Catholijn M. Jonker, Joost Broekens, Thomas M. Moerland","submitted_at":"2018-05-24T11:33:49Z","abstract_excerpt":"A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, navigation and self-driving cars. This paper presents the necessary theoretical extensions of Alpha Zero to deal with continuous action space. We also provide some preliminary experiments on the Pendulum swing-up task, empirically showing the feasibility of our approach. Thereby, t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1805.09613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T11:33:49Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"20f17949905343727da4eb5ad0b985e91ac2935c77848aab69c4d68d7cc4b769","abstract_canon_sha256":"b44d52c8c4de48c61243f335b1745c55cb6519775790c8c1937ac260f974888a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:03.403569Z","signature_b64":"Vwfihvk8JxExMfzHtzUM930Z24ZfcvdXllRhF1WSwisdQ1TlHgzgtN9eWX7L0nEfS9nx/XDflsqSVotwbCuiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24b39fc7ff7d23eb0f8d5ce22b88ab4b7f89c8eab2ec00164a505807a4137559","last_reissued_at":"2026-05-18T00:15:03.400137Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:03.400137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A0C: Alpha Zero in Continuous Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO","cs.SY"],"primary_cat":"stat.ML","authors_text":"Aske Plaat, Catholijn M. Jonker, Joost Broekens, Thomas M. Moerland","submitted_at":"2018-05-24T11:33:49Z","abstract_excerpt":"A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, navigation and self-driving cars. This paper presents the necessary theoretical extensions of Alpha Zero to deal with continuous action space. We also provide some preliminary experiments on the Pendulum swing-up task, empirically showing the feasibility of our approach. Thereby, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09613","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1805.09613","created_at":"2026-05-18T00:15:03.400228+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09613v1","created_at":"2026-05-18T00:15:03.400228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09613","created_at":"2026-05-18T00:15:03.400228+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESZZ7R77PUR6","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESZZ7R77PUR6WD4N","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESZZ7R77","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN","json":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN.json","graph_json":"https://pith.science/api/pith-number/ESZZ7R77PUR6WD4NLTRCXCFLJN/graph.json","events_json":"https://pith.science/api/pith-number/ESZZ7R77PUR6WD4NLTRCXCFLJN/events.json","paper":"https://pith.science/paper/ESZZ7R77"},"agent_actions":{"view_html":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN","download_json":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN.json","view_paper":"https://pith.science/paper/ESZZ7R77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09613&json=true","fetch_graph":"https://pith.science/api/pith-number/ESZZ7R77PUR6WD4NLTRCXCFLJN/graph.json","fetch_events":"https://pith.science/api/pith-number/ESZZ7R77PUR6WD4NLTRCXCFLJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/action/storage_attestation","attest_author":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/action/author_attestation","sign_citation":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/action/citation_signature","submit_replication":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/action/replication_record"}},"created_at":"2026-05-18T00:15:03.400228+00:00","updated_at":"2026-05-18T00:15:03.400228+00:00"}